Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 9315
    Prev
    Next
    INDEX
    Explanations

    names of people, with a focus on the last name "Payne."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific names, particularly "Payne," "MacDonald," and "Pearson."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Orche
    -0.79
     fel
    -0.78
    berus
    -0.77
     Flavoring
    -0.76
     cess
    -0.75
    Android
    -0.75
    20439
    -0.74
    yout
    -0.74
    zbollah
    -0.72
     holog
    -0.71
    POSITIVE LOGITS
     MacDonald
    2.16
     Pearson
    2.13
     Atkinson
    2.02
     Stephenson
    2.01
     Chapman
    1.97
     Payne
    1.96
     Davies
    1.96
     Rowe
    1.95
     Perkins
    1.94
     Fowler
    1.92
    Activations Density 0.058%

    No Known Activations